Upload tokenizer

special_tokens_map.json

@@ -13,5 +13,11 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|finetune_right_pad_id|>"
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -2050,13 +2050,18 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
+  "chat_template": "{%- for message in messages %}\n    {%- if message['role'] == 'user' %}\n        {{- bos_token + '<|start_header_id|>user<|end_header_id|>' + message['content'].strip() + '<|eot_id|>' }}\n    {%- elif message['role'] == 'assistant' %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>'  + message['content'] + eos_token }}\n    {%- endif %}\n{%- endfor %}\n",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|end_of_text|>",
+  "max_length": 131072,
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 131072,
   "pad_token": "<|finetune_right_pad_id|>",
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "stride": 0,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first"
 }